MouSi: Poly-Visual-Expert Vision-Language Models
Paper • 2401.17221 • Published • 9
AI & ML interests
Our research interests are mainly in natural language processing and machine learning. We aim to build efficient, effective and ethical models for computing human languages.
TaoJi
authored 7
papers about 1 year ago
LongHeads: Multi-Head Attention is Secretly a Long Context Processor
Paper • 2402.10685 • Published • 1
Length Generalization of Causal Transformers without Position Encoding
Paper • 2404.12224 • Published • 1
AntLM: Bridging Causal and Masked Language Models
Paper • 2412.03275 • Published
Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs
Paper • 2502.14837 • Published • 4
Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs
Paper • 2410.11302 • Published
Investigating and Mitigating Object Hallucinations in Pretrained Vision-Language (CLIP) Models
Paper • 2410.03176 • Published
RmZeta
updated 2
models almost 2 years ago